org.openimaj.image.feature.local.engine

Class MinMaxDoGSIFTEngine

java.lang.Object

org.openimaj.image.feature.local.engine.MinMaxDoGSIFTEngine

All Implemented Interfaces:

Engine<MinMaxKeypoint,FImage>

@Reference(type=Inproceedings,
           author={"Jonathon Hare","Sina Samangooei","Paul Lewis"},
           title="Efficient clustering and quantisation of SIFT features: Exploiting characteristics of the SIFT descriptor and interest region detectors under image inversion",
           year="2011",
           booktitle="The ACM International Conference on Multimedia Retrieval (ICMR 2011)",
           month="April",
           publisher="ACM Press")
public class MinMaxDoGSIFTEngine
extends Object
implements Engine<MinMaxKeypoint,FImage>

A modified implementation of Lowe's difference-of-Gaussian detector and SIFT feature extraction technique that also records whether features are detected at local minima or maxima by looking at the sign of the difference of Gaussian. This information can then be used for enhancing matching or clustering.

Internally, this class is identical to DoGSIFTEngine, but uses a OctaveMinMaxKeypointCollector instead of an OctaveKeypointCollector.

Author:

Jonathon Hare (jsh2@ecs.soton.ac.uk)

Constructor Summary

Constructors

Constructor and Description
MinMaxDoGSIFTEngine() Construct a MinMaxDoGSIFTEngine with the default options.
MinMaxDoGSIFTEngine(DoGSIFTEngineOptions<FImage> options) Construct a MinMaxDoGSIFTEngine with the given options.

Method Summary

Modifier and Type	Method and Description
LocalFeatureList<MinMaxKeypoint>	findFeatures(FImage image) Find local features in the given image and return them.
DoGSIFTEngineOptions<FImage>	getOptions() Get the options for this engine.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

MinMaxDoGSIFTEngine

public MinMaxDoGSIFTEngine()

Construct a MinMaxDoGSIFTEngine with the default options.

MinMaxDoGSIFTEngine

public MinMaxDoGSIFTEngine(DoGSIFTEngineOptions<FImage> options)

Construct a MinMaxDoGSIFTEngine with the given options.

Parameters:

options - the options

Method Detail

findFeatures

public LocalFeatureList<MinMaxKeypoint> findFeatures(FImage image)

Description copied from interface: Engine

Find local features in the given image and return them.

Specified by:

findFeatures in interface Engine<MinMaxKeypoint,FImage>

Parameters:

image - the image

Returns:

the features.

getOptions

public DoGSIFTEngineOptions<FImage> getOptions()

Get the options for this engine.

Returns:

the options for this engine